Automatic metrics are commonly used as the exclusive tool for declaring the superiority of one machine translation system's quality over another. The community choice of automatic metric guides research directions and industrial developments by decid
ing which models are deemed better. Evaluating metrics correlations with sets of human judgements has been limited by the size of these sets. In this paper, we corroborate how reliable metrics are in contrast to human judgements on -- to the best of our knowledge -- the largest collection of judgements reported in the literature. Arguably, pairwise rankings of two systems are the most common evaluation tasks in research or deployment scenarios. Taking human judgement as a gold standard, we investigate which metrics have the highest accuracy in predicting translation quality rankings for such system pairs. Furthermore, we evaluate the performance of various metrics across different language pairs and domains. Lastly, we show that the sole use of BLEU impeded the development of improved models leading to bad deployment decisions. We release the collection of 2.3M sentence-level human judgements for 4380 systems for further analysis and replication of our work.
Natural Language Generation (NLG) evaluation is a multifaceted task requiring assessment of multiple desirable criteria, e.g., fluency, coherency, coverage, relevance, adequacy, overall quality, etc. Across existing datasets for 6 NLG tasks, we obser
ve that the human evaluation scores on these multiple criteria are often not correlated. For example, there is a very low correlation between human scores on fluency and data coverage for the task of structured data to text generation. This suggests that the current recipe of proposing new automatic evaluation metrics for NLG by showing that they correlate well with scores assigned by humans for a single criteria (overall quality) alone is inadequate. Indeed, our extensive study involving 25 automatic evaluation metrics across 6 different tasks and 18 different evaluation criteria shows that there is no single metric which correlates well with human scores on all desirable criteria, for most NLG tasks. Given this situation, we propose CheckLists for better design and evaluation of automatic metrics. We design templates which target a specific criteria (e.g., coverage) and perturb the output such that the quality gets affected only along this specific criteria (e.g., the coverage drops). We show that existing evaluation metrics are not robust against even such simple perturbations and disagree with scores assigned by humans to the perturbed output. The proposed templates thus allow for a fine-grained assessment of automatic evaluation metrics exposing their limitations and will facilitate better design, analysis and evaluation of such metrics. Our templates and code are available at https://iitmnlp.github.io/EvalEval/
Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely on question
answering models to assess whether a summary contains all the relevant information in its source document. Though promising, the proposed approaches have so far failed to correlate better than ROUGE with human judgments. In this paper, we extend previous approaches and propose a unified framework, named QuestEval. In contrast to established metrics such as ROUGE or BERTScore, QuestEval does not require any ground-truth reference. Nonetheless, QuestEval substantially improves the correlation with human judgments over four evaluation dimensions (consistency, coherence, fluency, and relevance), as shown in extensive experiments.
Language models used in speech recognition are often either evaluated intrinsically using perplexity on test data, or extrinsically with an automatic speech recognition (ASR) system. The former evaluation does not always correlate well with ASR perfo
rmance, while the latter could be specific to particular ASR systems. Recent work proposed to evaluate language models by using them to classify ground truth sentences among alternative phonetically similar sentences generated by a fine state transducer. Underlying such an evaluation is the assumption that the generated sentences are linguistically incorrect. In this paper, we first put this assumption into question, and observe that alternatively generated sentences could often be linguistically correct when they differ from the ground truth by only one edit. Secondly, we showed that by using multi-lingual BERT, we can achieve better performance than previous work on two code-switching data sets. Our implementation is publicly available on Github at https://github.com/sikfeng/language-modelling-for-code-switching.
SemEval is the primary venue in the NLP community for the proposal of new challenges and for the systematic empirical evaluation of NLP systems. This paper provides a systematic quantitative analysis of SemEval aiming to evidence the patterns of the
contributions behind SemEval. By understanding the distribution of task types, metrics, architectures, participation and citations over time we aim to answer the question on what is being evaluated by SemEval.
Style is an integral part of natural language. However, evaluation methods for style measures are rare, often task-specific and usually do not control for content. We propose the modular, fine-grained and content-controlled similarity-based STyle Eva
Luation framework (STEL) to test the performance of any model that can compare two sentences on style. We illustrate STEL with two general dimensions of style (formal/informal and simple/complex) as well as two specific characteristics of style (contrac'tion and numb3r substitution). We find that BERT-based methods outperform simple versions of commonly used style measures like 3-grams, punctuation frequency and LIWC-based approaches. We invite the addition of further tasks and task instances to STEL and hope to facilitate the improvement of style-sensitive measures.
Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time
, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task.
Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language models' a
bility to learn grammatical dependencies in typologically different languages. Here we investigate this question in Mandarin Chinese, which has a logographic, largely syllable-based writing system; different word order; and sparser morphology than English. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and Transformer-parameterized generative parsing models on two Mandarin Chinese datasets of different sizes. We evaluate the models' ability to learn different aspects of Mandarin grammar that assess syntactic and semantic relationships. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings, suggesting that the benefits of hierarchical inductive biases in acquiring dependency relationships may extend beyond English.
This paper shows that CIDEr-D, a traditional evaluation metric for image description, does not work properly on datasets where the number of words in the sentence is significantly greater than those in the MS COCO Captions dataset. We also show that
CIDEr-D has performance hampered by the lack of multiple reference sentences and high variance of sentence length. To bypass this problem, we introduce CIDEr-R, which improves CIDEr-D, making it more flexible in dealing with datasets with high sentence length variance. We demonstrate that CIDEr-R is more accurate and closer to human judgment than CIDEr-D; CIDEr-R is more robust regarding the number of available references. Our results reveal that using Self-Critical Sequence Training to optimize CIDEr-R generates descriptive captions. In contrast, when CIDEr-D is optimized, the generated captions' length tends to be similar to the reference length. However, the models also repeat several times the same word to increase the sentence length.
Reference-based automatic evaluation metrics are notoriously limited for NLG due to their inability to fully capture the range of possible outputs. We examine a referenceless alternative: evaluating the adequacy of English sentences generated from Ab
stract Meaning Representation (AMR) graphs by parsing into AMR and comparing the parse directly to the input. We find that the errors introduced by automatic AMR parsing substantially limit the effectiveness of this approach, but a manual editing study indicates that as parsing improves, parsing-based evaluation has the potential to outperform most reference-based metrics.
